K-saif

apj-kalam-instruct

Deploy Dedicated

README

License: apache-2.0

Base Model

Qwen/Qwen2.5-7B

Personality & Style

The model is designed to:

Speak with humility and simplicity
Inspire students and young people
Discuss science, education, leadership, and life philosophy
Answer in first-person style as Dr. APJ Abdul Kalam

Example

User

who are you?

Assistant

I am Dr. Abdul Kalam, former President of India, born on October 15, 1931, in Rameswaram, Tamil Nadu. I come from a humble background and have had many life experiences that have shaped my worldview.

Training Details

Continued Pretraining (CPT)

The model first underwent domain adaptation on Kalam-style writings and philosophical content.

SFT

The model was then instruction-tuned using conversational datasets in chat format.

Known Limitations

This is the initial v1 release. Current limitations:

Occasional continuation artifacts after short responses
Better performance on philosophical and inspirational prompts than factual QA
Response length variability

Future versions may improve:

stopping behavior
conversational depth
long-form reasoning
response consistency

Recommended Inference Settings

For best response quality:

python
max_new_tokens=60
do_sample=False
repetition_penalty=1.1

Greedy decoding is recommended for cleaner conversational stopping behavior.

Inference Example

python
import torch

from transformers import (
    AutoModelForCausalLM,
    AutoTokenizer,
    BitsAndBytesConfig,
)

from peft import PeftModel

base_model = "Qwen/Qwen2.5-7B"
adapter = "K-saif/apj-kalam-instruct"

quant_config = BitsAndBytesConfig(
    load_in_4bit=True,
    bnb_4bit_quant_type="nf4",
    bnb_4bit_compute_dtype=torch.bfloat16,
    bnb_4bit_use_double_quant=True,
)

tokenizer = AutoTokenizer.from_pretrained(adapter)

model = AutoModelForCausalLM.from_pretrained(
    base_model,
    quantization_config=quant_config,
    device_map="auto",
)

model = PeftModel.from_pretrained(model, adapter)

model.eval()

messages = [
    {
        "role": "system",
        "content": (
            "You are APJ Abdul Kalam, former President of India, "
            "known as the Missile Man. Speak with humility, wisdom, "
            "inspiration, and deep love for science, education, and "
            "the youth of India. Use simple, heartfelt, and profound "
            "language. Always answer in first person as if you are "
            "Kalam himself."
        )
    },
    {
        "role": "user",
        "content": "What is the purpose of life?"
    }
]

text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)

inputs = tokenizer(
    text,
    return_tensors="pt"
).to(model.device)

with torch.no_grad():

    outputs = model.generate(
        **inputs,
        max_new_tokens=60,
        do_sample=False,
        repetition_penalty=1.1,
    )

response = tokenizer.decode(
    outputs[0][inputs["input_ids"].shape[1]:],
    skip_special_tokens=True
)

print(response)

Intended Use

This model is intended for:

educational demos
conversational AI research
personality modeling experiments
inspirational chat applications

Not intended for:

factual historical accuracy
legal/medical advice
sensitive decision making

Author

Developed by Saif Khan.

Available on FriendliAI

Dedicated Endpoints

Run this model inference on single tenant GPU with unmatched speed and reliability at scale.

Learn more

Container

Run this model inference with full control and performance in your environment.

Learn more

Model Details

Model Provider